Cormac Brick

Enjoy family, food, outdoors.
On week days I spend time in my dining-room/office working on HW/SW/Systems for AI acceleration...

[AI Engineer @aiDotEngineer]

TLMs: Tiny LLMs and Agents on Edge Devices with @cormacb

https://t.co/u0fHD7j5kZ

Function Gemma ships at 270 million parameters and runs nearly 2,000 tokens per second prefill on a Pixel 7. Out of the box, it hits 46% accuracy on a fixed set of app intents. Fine tune on a synthetically generated dataset and that clears 90% on eight of ten functions.

Cormac walks through the two paths developers have for on device AI: a skill harness built on Gemma 4 with a restaurant roulette demo running fully on device. Then Eloquent, a production transcription app built by chaining two sub billion parameter models together.

cc @osanseviero

[Cormac Brick @cormacb]

@aiDotEngineer great to see this, really enjoyed speaking to such an engaged audience -- great event

[Google Gemma @googlegemma]

Check out this video on how to run Gemma 4 locally on an iPhone!

It runs completely offline and handles long context, meaning no data plan, no API calls, and no monthly fees required.

[Cormac Brick @cormacb]

@osanseviero @swyx @patloeber @nick_kango That was fun! Looking forward to the first Gemma4 Runtime in SF!

[Omar Sanseviero @osanseviero]

Our first successful Gemma 4 Runtime in London with @swyx @patloeber @nick_kango @cormacb and others! 💎Great to go out for a run and talk about Gemma, agents, evals and more

[Cormac Brick @cormacb]

Hello @memdotai 👋 just setting up my Twitter flow. Here's my validation code: TyWbWXsnd84F3Pb0Q68l

[Patrick Collison @patrickc]

My letter to the editor in response to https://t.co/p5KtNOiCnm.

[Jesslyn 🇮🇩 @jtannady]

Do you like #AnimalCrossing

Do you like artificial intelligence 💻

Do you like workshops 🧠

https://t.co/NQzLpkQs7P

[Cormac Brick @cormacb]

@vincentbrowne 1. Cheltenham, 2. northern Italy flights

[Cormac Brick @cormacb]

@sriramk Acorn computers in UK in early 80s. (BBC micro, and ARM was originally acorn risk machines)

[Cormac Brick @cormacb]

@culurciello In silicon companies, there is a strong bias towards more silicon.

[Cormac Brick @cormacb]

Awesome (in the literal sense)...

[Ryan Lowe 🥞 @ryan_t_lowe]

Here's a ridiculous result from the @OpenAI GPT-2 paper (Table 13) that might get buried --- the model makes up an entire, coherent news article about TALKING UNICORNS, given only 2 sentences of context.

WHAT??!!

[Cormac Brick @cormacb]

This is really cool project, congrats to Lucian and all involved -- battery life increase from 6 weeks to 1.5 years!

https://t.co/QubaftqS8t https://t.co/C2HIOfDWCq

[Cormac Brick @cormacb]

https://t.co/RFYIS2qfW4

[Cormac Brick @cormacb]

We are hiring in Seattle to join the https://t.co/LKBtDNhPbU crew that recently joined us through acquisition. Great opportunity to join a top class team working on one of the new frontiers of CS/ML. https://t.co/4R4677N1AM

[Pete Warden @petewarden]

My colleague Raghu has just released "Quantizing deep convolutional networks for efficient inference" - https://t.co/D87ziflTqd
This white paper covers practical quantization approaches for most common CNNs in @TensorFlow, I think it will be super useful!

[Andrej Karpathy @karpathy]

It is starting to look like deep learning workflows of the future feature autotuned architectures running with autotuned compute schedules across arbitrary backends. I don't know if I should be excited or scared.

[Remi El-Ouazzane @relouazzane]

Intel and Microsoft Enable AI Inference at the Edge with Intel Movidius Vision Processing Units on Windows ML https://t.co/1jgQbtA6T3

[Cormac Brick @cormacb]

Thanks #aerlingus for (hopefully) getting ei145 out today #Sneachtageddon #sneachta #StormEmma

[Cormac Brick @cormacb]

Long but really interesting... https://t.co/XIwT5rQKQF